Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    names or references related to a specific person or entity called "Da"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    sburgh
    -0.95
    sburg
    -0.80
    ship
    -0.76
    tions
    -0.72
    eele
    -0.72
    hetti
    -0.70
    ULAR
    -0.70
    dal
    -0.69
    rations
    -0.68
    lessly
    -0.67
    POSITIVE LOGITS
    isy
    1.25
    ft
    1.06
    emon
    1.01
    uthor
    0.98
    emonic
    0.97
    ivari
    0.96
    quer
    0.95
    iley
    0.92
    uman
    0.91
    qu
    0.90
    Act Density 0.027%

    No Known Activations